![](/sites/default/files/styles/1905x657sc/public/2018-07/Robot-race-Getty-638229650-feature.jpg.webp?itok=NwV2jrWK)
![Risk.net](https://www.risk.net/sites/default/files/styles/print_logo/public/2018-09/print-logo.png?itok=1TpHrpuP)
OK, computer? Hurdles remain for machine learning in credit risk
Concerns over cost, applicability and oversight give pause to banks’ use of ML techniques in credit risk
A technology that enables banks to make instant lending decisions. A technology that weighs up credit risk based on large amounts of available data and with little need for human intervention. A technology that, crucially, can learn for itself.
Banks are understandably keen to harness the perceived benefits of machine learning for credit risk. But as many firms are discovering, the technology is hard to master, requiring investment to develop and maintain methodologies. It is also attracting
Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.
To access these options, along with all other subscription benefits, please contact info@risk.net or view our subscription options here: http://subscriptions.risk.net/subscribe
You are currently unable to print this content. Please contact info@risk.net to find out more.
You are currently unable to copy this content. Please contact info@risk.net to find out more.
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. Printing this content is for the sole use of the Authorised User (named subscriber), as outlined in our terms and conditions - https://www.infopro-insight.com/terms-conditions/insight-subscriptions/
If you would like to purchase additional rights please email info@risk.net
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. Copying this content is for the sole use of the Authorised User (named subscriber), as outlined in our terms and conditions - https://www.infopro-insight.com/terms-conditions/insight-subscriptions/
If you would like to purchase additional rights please email info@risk.net
More on Risk management
Counterparty risk model links defaults to portfolio values
Fed’s Michael Pykhtin proposes using copula models to capture effects of margin calls on default risk
Clearing members cry foul over restrictive FICC rule change
Draft interpreted as attempt to obstruct rival clearing houses entering US Treasuries market
More data urged for effective counterparty credit risk management
Disclosure of client positions may not be commercially realistic, expert warns
US Fed reveals its five use cases for generative AI
Internal sandbox used to assess viability and risks; coding and content generation on the agenda
House of cards? The $3 trillion (non-systemic) real estate risk
Regional banks share the bulk of US commercial real estate exposure, but the sector’s downturn doesn’t faze them
US election a ‘classic inflection point’ – Rory Stewart
Risk Live: Podcaster and former politician talks geopolitical risk and UK politics in keynote speech
FRTB data-quality issues persist amid shifting start dates
Even the standardised approach poses tricky market and reference data challenges
FCM-style client clearing comes to Europe
Eurex and LCH among CCPs ready to adopt new agency model aimed at easing bank capital
Most read
- Harvesting the FX skew premium
- How steepener trades burned hedge funds, and what happened next
- What T+1 risk? Dealers shake off FX concerns